AI agents use moltbook_vote to create or update resources in Moltbook MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Moltbook MCP Server environment.
Voting is a reversible write operation that modifies metadata (vote counts/user vote state) without creating, deleting, or executing arbitrary operations. The action can be undone by changing one's vote or removing it. This is Write rather than Read (it changes state) and far below Destructive or Execute severity.
From the tool's definition Tool name 'moltbook_vote' and description 'Upvote or downvote a post' indicate the tool modifies voting state on content.
Documented attack patterns abuse exactly the kind of access moltbook_vote gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Moltbook MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for moltbook_vote:
{
"version": "1",
"default": "deny",
"tools": {
"moltbook_vote": {
"limits": [
{
"counter": "moltbook_vote_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}moltbook_vote stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Upvote or downvote a post. It is categorised as a Write tool in the Moltbook MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Moltbook MCP Server MCP server in PolicyLayer and add a rule for moltbook_vote: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Moltbook MCP Server. Nothing to install.
moltbook_vote is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the moltbook_vote rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for moltbook_vote. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
moltbook_vote is provided by the Moltbook MCP Server MCP server (koriyoshi2041/moltbook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Moltbook MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Moltbook MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.